Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3450 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3287. Min Range: -5.3287
Max Act: 5.3287. Min Act: -0.1700
Data Index: 3616723 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3287. Min Range: -5.3287
Max Act: 5.1412. Min Act: -0.1700
Data Index: 8035993 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3287. Min Range: -5.3287
Max Act: 5.1412. Min Act: -0.1700
Data Index: 8616688 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3287. Min Range: -5.3287
Max Act: 5.1099. Min Act: -0.1700
Data Index: 8616691 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3287. Min Range: -5.3287
Max Act: 5.0474. Min Act: -0.1700
Data Index: 8616689 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3287. Min Range: -5.3287
Max Act: 5.0162. Min Act: -0.1700
Data Index: 252604 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3287. Min Range: -5.3287
Max Act: 5.0474. Min Act: -0.1700
Data Index: 8616692 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3287. Min Range: -5.3287
Max Act: 4.9224. Min Act: -0.1700
Data Index: 8616690 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3287. Min Range: -5.3287
Max Act: 4.8912. Min Act: -0.1700
Data Index: 4837392 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3287. Min Range: -5.3287
Max Act: 4.8599. Min Act: -0.1700
Data Index: 967358 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3287. Min Range: -5.3287
Max Act: 4.7974. Min Act: -0.1700
Data Index: 5502463 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3287. Min Range: -5.3287
Max Act: 4.7974. Min Act: -0.1700
Data Index: 8616693 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3287. Min Range: -5.3287
Max Act: 4.7662. Min Act: -0.1700
Data Index: 1852357 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3287. Min Range: -5.3287
Max Act: 4.7662. Min Act: -0.1700
Data Index: 1953009 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3287. Min Range: -5.3287
Max Act: 4.7974. Min Act: -0.1700
Data Index: 758845 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3287. Min Range: -5.3287
Max Act: 4.7662. Min Act: -0.1700
Data Index: 6967198 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3287. Min Range: -5.3287
Max Act: 4.7349. Min Act: -0.1700
Data Index: 7568568 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3287. Min Range: -5.3287
Max Act: 4.7349. Min Act: -0.1700
Data Index: 4652618 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3287. Min Range: -5.3287
Max Act: 4.6724. Min Act: -0.1700
Data Index: 3835290 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3287. Min Range: -5.3287
Max Act: 4.7037. Min Act: -0.1700
Data Index: 7928870 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #19